Optimal average value convergence in nonhomogeneous Markov decision processes (Q1323097)
From MaRDI portal
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Optimal average value convergence in nonhomogeneous Markov decision processes |
scientific article |
Statements
Optimal average value convergence in nonhomogeneous Markov decision processes (English)
0 references
9 May 1994
0 references
This paper deals with an infinite state nonhomogeneous Markov decision process with average reward criterion. The authors proved the following two structural results: (1) Under the Doeblin condition, the problem is equivalent to a discounted problem. (2) Under the same condition, the optimal finite horizon average values converge to the infinite horizon optimal one.
0 references
infinite state nonhomogeneous Markov decision process
0 references
average reward criterion
0 references